Tag: #on-device ai

Apple’s M6 and M5 Ultra Show Two Very Different Ways to Build a Faster Mac
hardware Aug 25, 2026 6 min read

Apple’s M6 and M5 Ultra Show Two Very Different Ways to Build a Faster Mac

Apple’s M6 and M5 Ultra are not direct rivals: M6 brings a 2 nm design and dual Neural Engines to the Mac mini, while M5 Ultra uses four connected dies, huge memory, and workstation-class bandwidth in Mac Studio. Here’s what those architectural choices mean for coding, creative work, gaming, and running large AI models locally.

by ahsan
#apple silicon #m5 ultra #m6 #on-device ai #unified memory
Bonsai 27B on a Phone: How 1‑bit & Ternary Quantization Make Agentic AI Possible
ai systems & inference Jul 15, 2026 7 min read

Bonsai 27B on a Phone: How 1‑bit & Ternary Quantization Make Agentic AI Possible

Bonsai 27B is a 27B-class multimodal model announced by PrismML that they claim can run on a phone by using 1-bit or ternary weight formats with group-wise FP16 scaling. The architecture also includes on-device vision support and speculative decoding to make long agentic loops practical without shipping user data to the cloud.

by ahsan
#agentic systems #llm quantization #multimodal #on-device ai #speculative decoding